zpn/clintox
收藏资源简介:
clintox数据集是MoleculeNet中的一个数据集,包含FDA批准的药物和因毒性原因未能通过临床试验的药物的定性数据。该数据集使用CT_TOX任务。每个数据实例包含分子的SMILES和SELFIES表示,以及临床试验毒性(或无毒)的目标值。数据集按80/10/10的比例分为训练集、验证集和测试集,使用scaffold分割方法。数据最初由斯坦福大学的Pande Group生成,并以MIT许可证发布。
The ClinTox dataset is a dataset within MoleculeNet, containing qualitative data on FDA-approved drugs and drugs that failed clinical trials due to toxicity. It utilizes the CT_TOX task. Each data instance includes the SMILES and SELFIES representations of the molecule, alongside the target value for clinical trial toxicity (or non-toxicity). The dataset is split into training, validation and test sets with an 80/10/10 ratio via the scaffold splitting method. The data was originally generated by the Pande Group at Stanford University and released under the MIT License.
数据集概述
数据集名称
- 名称: clintox
数据集属性
- 语言: 单语种(monolingual)
- 许可证: MIT
- 大小: 1K<n<10K
- 标签:
- bio
- bio-chem
- molnet
- molecule-net
- biophysics
- 任务类别: other
数据集描述
- 概述:
clintox是 MoleculeNet 中的一个数据集,包含FDA批准的药物和因毒性原因未通过临床试验的药物的定性数据。此数据集使用CT_TOX任务。
数据集结构
- 数据字段:
- 数据分割: 采用80/10/10的训练/验证/测试分割,使用scaffold split方法。
数据集创建
- 源数据: 数据最初由斯坦福大学的Pande Group生成。
- 许可证: 原始发布为MIT许可证。
引用信息
@misc{https://doi.org/10.48550/arxiv.1703.00564, doi = {10.48550/ARXIV.1703.00564}, url = {https://arxiv.org/abs/1703.00564}, author = {Wu, Zhenqin and Ramsundar, Bharath and Feinberg, Evan N. and Gomes, Joseph and Geniesse, Caleb and Pappu, Aneesh S. and Leswing, Karl and Pande, Vijay}, keywords = {Machine Learning (cs.LG), Chemical Physics (physics.chem-ph), Machine Learning (stat.ML), FOS: Computer and information sciences, FOS: Computer and information sciences, FOS: Physical sciences, FOS: Physical sciences}, title = {MoleculeNet: A Benchmark for Molecular Machine Learning}, publisher = {arXiv}, year = {2017}, copyright = {arXiv.org perpetual, non-exclusive license} }




